Unverified50% confidenceBenchmarkExact time
Under matching the same model and comparable budgets, H1 matches or Pareto-dominates custom systems on multiple benchmarks including Putnam Bench, and has solved eight open conjecture problems.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
11/17/2026
First Seen
Valid until: 2/15/2027
Sources
Simple Loop Tops Automated Theorem Proving: The Bitter Lesson Revisited
bilibili熊二等兵11/1/2026
Related Entities
Related Claims
UnverifiedThe study compares five budget-matched continuous optimizers (including a hybrid swarm optimization with L-BFGS-B refinement) against the candidate-pool method, covering 11 problems (dimensions from 2 to 100).71% similarUnverifiedThe class-mean direction outperformed the null hypotheses of random subspace, label permutation, and covariance matching in balanced accuracy in all 12 model-label tests.65% similarUnverifiedIn testing, all nine inputs of varying difficulty were routed through demo-smart, and the actually selected models matched expectations in every case.64% similarUnverifiedVariance-based contrastive optimization identifies problems in planning and tool invocation by contrasting samples with different performance levels.64% similarUnverifiedStandard flow matching inference requires sampling from a prior and numerically integrating the ODE, thus requiring multiple iterations.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1180792API
curl https://kongchang.com/api/v1/knowledge/claims/1180792MCP
get_claim(id=1180792)